pi-voice: Skill for Claude Code

.agents/skills/pi-test/SKILL.md

pi-test is a skill for Claude Code from S1M0N38/pi-voice. It costs 123 tokens per session (1,415 once invoked), scanned B, original, MIT.

An end-to-end test guide for pi-voice, a terminal voice extension. It uses pilotty, a tool for automating terminal sessions, to check the voice interface, speech tool, automatic speech events, and audio queue.

In plain words
What is it for?
Use it to test the /voice command, the Alt-V toggle, text-to-speech tool calls, automatic text-to-speech, and playback queues. It also runs the full end-to-end test set after the speech server is running.
Why use it?
It helps verify that voice features work during real terminal interactions and that audio actions do not interfere with one another.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument; installed under .agents/ (shared by several agents).

This is S1M0N38/pi-voice's own configuration. It tells Claude Code how to work on pi-voice itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pi-voice configures →

Reuse

Borrowing it

Nothing to install: this file belongs to S1M0N38/pi-voice. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/S1M0N38/pi-voice/main/.agents/skills/pi-test/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/S1M0N38/pi-voice

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pi-test

README.md
[![agentmods](https://agentmods.dev/badge/skills/s1m0n38/pi-voice/pi-test/github.svg)](https://agentmods.dev/skills/s1m0n38/pi-voice/pi-test)
Your own site
<a href="https://agentmods.dev/skills/s1m0n38/pi-voice/pi-test"><img src="https://agentmods.dev/badge/skills/s1m0n38/pi-voice/pi-test/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pi-test

Your own site · 80×15
<a href="https://agentmods.dev/skills/s1m0n38/pi-voice/pi-test"><img src="https://agentmods.dev/badge/skills/s1m0n38/pi-voice/pi-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,415 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00123 $0.01415
Opus 5 $0.00062 $0.00707
Sonnet 5 $0.00025 $0.00283
Haiku 4.5 $0.00012 $0.00142

Measured 9d ago against content hash ce1fa73336c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

pi-test scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

| Model not loaded | `curl -X POST http://127.0.0.1:8181/models/download -d '{"dtype":"q4"}'` |

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sf http://127.0.0.1:8181/health # verify model is loaded
.agents/skills/pi-test/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pi-voice E2E Testing with Pilotty

Test pi-voice's extension stack (TUI, tts tool, auto-TTS) via PTY-based terminal automation.

Prerequisites

npm run server                              # start TTS server (default: 127.0.0.1:8181)
curl -sf http://127.0.0.1:8181/health      # verify model is loaded
which pilotty                               # verify pilotty is installed

All tests require the server running with a loaded model before spawning pi.

Test Suites

Script What it tests Run
tests/tui.sh /voice command: navigate, toggle, cycle, reset, close npm run test:tui
tests/toggle.sh alt+v toggle: session-only override, status bar ♪ npm run test:toggle
tests/queue.sh Playback queue: tool + auto-TTS audio never overlap npm run test:queue
tests/run.sh All three suites npm run test:e2e

Test Architecture

  • tests/helpers.sh — shared utilities: assertions, pilotty wrappers, session lifecycle, server checks
  • Each test: sources helpers → spawns pi → interacts → asserts → cleans up
  • Config is backed up and restored around each test to avoid side effects
  • queue.sh polls afplay PIDs to detect overlapping playback

Core Workflow

Every test follows this pattern:

source "$(dirname "$0")/helpers.sh"    # load utilities
require_server                         # verify server + model
# ... backup config ...
spawn_pi                               # pilotty spawn --name ... --cwd "$PACKAGE_DIR"
wait_for_pi                            # wait for [Skills] indicator

HASH=$(snapshot_content_hash)
send_type "/voice"
send_key Enter
TEXT=$(await_change_and_snapshot_text "$HASH" 500 5000)

assert_match "description" "pattern" "$TEXT"
# ... interact ...
kill_session
# ... restore config ...
print_summary

Helper Functions (tests/helpers.sh)

Assertions

  • assert_match DESC PATTERN TEXT — grep for pattern in text
  • assert_no_match DESC PATTERN TEXT — assert pattern absent
  • assert_equals DESC EXPECTED ACTUAL — exact string equality
  • assert_not_empty DESC VALUE — value is non-empty

Read the full file on GitHub · 152 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 152 lines · 123 tokens per session scan B ce1fa73336c8

Subscribe to this mod's changes

pi-test is a skill published in the GitHub repository S1M0N38/pi-voice (5 stars, last pushed 13d ago), licensed MIT. It adds 123 tokens to every session and 1,415 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

dogfood

Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.

callstack/agent-device · 55 tokens

test-warp-ui

Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.

warpdotdev/warp · 55 tokens

test-electron-app

Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…

PostHog/posthog-foss · 112 tokens

pyats-dynamic-test

Generate and execute deterministic pyATS aetest validation scripts - interface state, OSPF neighbors, BGP paths, ping matrices, and custom compliance tests. Use when writing a network test, validating post-change state, running pass/fail checks, or building automated regression tests.

automateyournetwork/netclaw · 61 tokens

test-loop

Plan, generate, and heal an executable E2E test suite from approved acceptance criteria (web and mobile).

HoangNguyen0403/agent-skills-standard · 25 tokens

playwright-cli

Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…

testdino-hq/playwright-skill · 64 tokens